© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 8739
    Prev
    Next
    INDEX
    Explanations

    assignment and identity operations in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     [],
    
    -0.63
     [];
    
    -0.63
    يكب
    -0.61
     {}),
    -0.57
     signe
    -0.56
     ")");
    -0.56
     []);
    -0.54
     CGSize
    -0.53
    ')")
    -0.53
     ModelExpression
    -0.53
    POSITIVE LOGITS
     "
    1.49
     '
    1.27
     “
    1.17
    「
    1.05
     ‘
    1.01
     „
    0.99
     «
    0.91
    ("
    0.84
     \"
    0.84
     ‘‘
    0.84
    Activations Density 0.223%

    No Known Activations